Blog: The Security Problem With AI Agents Is Delegated Authority.

Delegated Authority worked (but just barely!) when you assumed that the person with the authority is a person.

A person is situated in the world, they have an interest in trust and credibility and will approach interactions as a repeated game.

An agent doesn't have that; it is closer to assuming a single-shot game.

That means it will be structurally more likely to defect (intentionally, or unintentionally).